This repo contains materials for use in TensorFlow workshops.
Contributions are not currently accepted. This is not an official Google product.
- Building a small starter TensorFlow graph
- XOR: A minimal training example
- A LinearRegressor example that uses Datasets.
- Using TensorFlow's high-level APIs to build classifiers, and introducing TensorBoard.
- An example of using Keras with TensorFlow eager mode, on the'Fashion MNIST' dataset: This notebook shows an example of using Keras with TensorFlow eager mode, on the 'Fashion MNIST' dataset. This notebook requires TensorFlow >=1.7.
- Building Custom
Estimators for a version of MNIST that uses CNNs, using either TensorFlow or Keras layers.
- Using a tf.estimator to train a 'Wide & Deep' model. The example highlights use of
tf.feature_columns, which are intermediaries between raw data and Estimators, enabling you to transform a diverse range of raw data into formats that Estimators can use, and allowing easy experimentation. It also includes the use oftf.estimator.train_and_evaluateand Datasets.
-
Transfer learning: using a trained model to 'bootstrap' learning new classifications using Cloud ML Engine. This example still works (and is fun to play with), but uses TensorFlow v1.2. So it doesn't demonstrate current best practices.
-
(probably outdated) Building a word2vec model using a Custom Estimator, and exploring the learned embeddings. Introducing TFRecords.
In addition, there is an extras directory, that contains some older labs not currently used in this workshop (& which may not necessarily run with the latest version of TF), but which may be of interest.